Paper-Conference

Argus: Hardware-Software Co-Scaling of Tensor Parallelism for Efficient LLM Training
GhostAccess: Attacking the GPU on the Multi-tenant Cloud via CPU LLC under Unified Memory
Uncovering Contention-Based Side-Channel Threats in AMD Zen Chiplet Architectures
TArCS: Trusted and Attack-Resilient Clock Source with TEE and RDMA
MegaZK: A Memory Efficient GPU System Accelerating End-to-end Zero-Knowledge Proof
Oral presentation.
PDF DOI
HybridSpec: Exploiting Hybrid-bonding Memory to Accelerate LLM Serving through Heterogeneous Architecture and Speculative Decoding
SSBench: Automated Characterization of Memory Dependence Predictors on Modern CPUs
Stone-Skimming: Attacking Big-Data Analytics Applications with Page Table Walk
DAC 1793, oral presentation.
SHMemora: Protective Key-Value Store on Distributed Shared Memory
Modern in-memory key-value stores (IMKVS) are essential for data-intensive applications but increasingly limited by memory capacity. …
DROW: Training-Free Load Speculative Execution Attacks on Apple Silicon

""